© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129642
    Prev
    Next
    INDEX
    Explanations

    document section labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.84
     or
    -1.66
     only
    -1.42
     first
    -1.40
     ONLY
    -1.36
     longstanding
    -1.36
     so
    -1.29
     invigor
    -1.27
     nahezu
    -1.27
     four
    -1.20
    POSITIVE LOGITS
    generally
    1.27
    ESPEC
    1.21
    creating
    1.21
    commonly
    1.19
    several
    1.19
    trying
    1.16
    often
    1.13
     Ninh
    1.13
    REFUND
    1.13
    omal
    1.12
    Activations Density 0.016%

    No Known Activations